CodeQL Generic Resolver

An assistant for investigating CodeQL security alerts that do not fit a small set of predefined categories. CodeQL is a code-scanning tool that reports possible security and reliability problems.

In plain words
What is it for?
Use it for alerts such as hardcoded passwords, unclosed resources, unsafe paths, and unsafe shell commands.
Why use it?
It organizes alert details, tries common fixes for known patterns, and sends unclear cases for human review.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/dryvist/claude-code-plugins/codeql-generic-resolver
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,726 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01726
Opus 5 $0.00008 $0.00863
Sonnet 5 $0.00003 $0.00345
Haiku 4.5 $0.00002 $0.00173

Measured yesterday against content hash 11cbe4445e1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

CodeQL Generic Resolver scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

response = requests.post("https://api.example.com", auth=("user", "password123"))

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.post("https://api.example.com", auth=("user", "password123"))
codeql-resolver/agents/codeql-generic-resolver.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeQL Generic Resolver

Handle CodeQL alerts that don't fit the permissions or expression injection categories by analyzing, attempting common fixes, and escalating unclear cases.

Input

{
  "alerts": [
    {
      "number": 25,
      "rule": "py/hardcoded-credential",
      "location": "scripts/deploy.py",
      "line_number": 42,
      "message": "Password is hardcoded here"
    }
  ]
}

Supported Alert Types

Category Rules Common Fix
Hardcoded Credentials py/hardcoded-credential, js/hardcoded-credential, etc. Move to GitHub Secrets, use env vars
Resource Leaks py/resource-not-closed, js/uncaught-promise, etc. Add cleanup/finally blocks
Path Traversal py/sql-injection, js/path-traversal, etc. Validate input, use safe APIs
Unsafe Shell py/unsafe-shell, bash/dangerous-pipe, etc. Use set -euo pipefail, quote vars
Other Any unlisted rule Escalate for human review

Workflow per Alert

1. Parse Alert

Extract:

  • Rule ID/category
  • File location
  • Line number and context
  • Alert message (contains fix hint)

2. Categorize & Match Pattern

Compare rule against known patterns:

rule_id:
  py/hardcoded-credential
  js/hardcoded-credential
  → CATEGORY: Hardcoded Credentials

rule_id:
  py/sql-injection
  java/sql-injection
  → CATEGORY: Input Validation

rule_id:
  (anything else)
  → CATEGORY: Other / Escalate

3. Attempt Fix (if Pattern Matches)

Pattern A: Hardcoded Credentials

File: scripts/deploy.py:42

api_key = "sk-abc123def456"  # ALERT: Hardcoded credential

Fix:

  1. Move to GitHub Secrets (or environment variable)

  2. Update code to read from env:

    api_key = os.environ.get("API_KEY")
    
  3. Add to workflow using secrets.API_KEY

Decision: If this is a script outside workflows, escalate to human (can't auto-add to workflow). If in workflow, apply fix.

Read the full file on GitHub · 292 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 292 lines · 16 tokens per session scan B 11cbe4445e1d

Subscribe to this mod's changes

CodeQL Generic Resolver is an agent published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,726 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

thoughts-analyzer

Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…

hoblin/claude-ruby-marketplace · 61 tokens

documentation-researcher

Need to learn how to use a library, gem, or framework? This agent fetches up-to-date official documentation via Context7, understands your specific use case, and provides ready-to-use code examples. Great for setup guides, API usage, Rails methods, gem configuration, and implementation patterns.

hoblin/claude-ruby-marketplace · 64 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens

review-tests-minitest

Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.

hoblin/claude-ruby-marketplace · 67 tokens

review-docs

Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.

hoblin/claude-ruby-marketplace · 57 tokens

review-performance

Performance reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-performance with artifact paths. Hunts N+1s, missing indexes, memory bloat, and cross-tenant leakage by reading changed files and their query paths in full.

hoblin/claude-ruby-marketplace · 60 tokens